Application questions. Theoretical questions
|
|
- Winfred Kennedy
- 5 years ago
- Views:
Transcription
1 The oral exam will last 30 minutes and will consist of one application question followed by two theoretical questions. Please find below a non exhaustive list of possible application questions. The list of theoretical question is instead exhaustive, i.e., it contains all the topics that you should learn about the course. Application questions 1. Summarize the building blocks of a visual odometry (VO) or visual SLAM (VSLAM) algorithm. 2. Augmented reality (AR) is a view of a physical scene augmented by computer-generated sensory inputs, such as data or graphics. Suppose you want to design an augmented reality system that super-imposes text labels to the image of real physical objects. Summarize the building blocks of an AR algorithm. 3. Suppose that your task is to reconstruct an object from different views. How do you proceed? 4. Building a panorama stitching application. Summarize the building blocks. 5. How would you design a mobile tourist app? The user points the phone in the direction of a landmark and the app displays tag with the name of it. How would you implement it? 6. Assume that we have several images downloaded from flicker showing the two towers of Grossmünster. Since such images were uploaded by different persons they will have different camera parameters (intrinsic and extrinsic), different lighting, different resolutions and so on. If you were supposed to create a 3D model of Grossmünster, what kind of approach would you use? Can you get a dense 3D model or it will be a sparse one? Please explain the pipeline that you propose for this scenario. 7. Assume that you move around a statue with a camera and take pictures in a way that the statue is not far from the camera and always completely visible in the image. If you were supposed to find out where the pictures were taken, what would you do with the images? What kind of approach would you use? Since the camera motion is around the statue, the images contain different parts of the statue. How do you deal with this problem? 8. Suppose that you have two robots exploring an environment, explain how the robots should localize themselves and each other with respect to the environment? What are the alternative solutions? Theoretical questions 01 Introduction Definition of VO. VO vs VSLAM vs SFM. Assumptions. Working principle and building blocks. Dense vs semi-dense vs sparse. Bundle Adjustment vs Pose graph optimization (formulas and explanation) Image Formation 1. Blur circle. 2. Pin-hole approximation (proof). 3. Definition of vanishing points and lines. Prove that the parallel lines intersect at vanishing points and show how to compute it mathematically. 4. How do you build an Ames room (the floor and the walls); try to sketch a concept.
2 5. Relation between field of view and focal length. 6. Perspective projection equations including lens distortion and world to camera projection (derivation of perspective equations in matrix form using homogeneous coordinates). Normalized image coordinates and geometric explanation. 7. Definition of general PnP problem (what s the minimum number of points and what are the degenerate configurations). Working principle of P3P algorithm (non-linear algorithm for calibrated cameras: what are the algebraic trigonometric equations that it attempts to solve?). How do we solve PnP using a linear algorithm (derive DLT equations for 3D object or planar grids) and what is the minimum number of point correspondences it requires, why? 8. Omnidirectional cameras (only definition of central and non central cameras): what type of mirror ensure central projection? Spherical model: illustrate equivalence between perspective and omnidirectional model. What do we mean by normalized image coordinates on the unit sphere? 9. Given an image and the associated camera pose, how would you superimpose a virtual object on the image (for example, a virtual cube). Describe the steps involved. 04 Filtering and edge detection 1. Working principle of filters: convolution vs correlation. Box filter vs Gaussian filter (what are the pros and cons of either one?). Median filter (when do we need a median filter?) Gaussian filters: why should we increase the size of the kernel if sigma is large (i.e., sigma close to the size of the kernel)? Boundary issues. 2. Edge detection: working principle with 1D signal; noise effects; differential property of convolution; how do we compute the first derivative along x and y? Laplacian of Gaussian operator: why should we use it and what effect does it have on the image? Properties of smoothing and derivative filters (what is the sum of the coefficients of a smoothing filter, and of a derivative filter?). Illustrate Canny edge detection. What is non-maxima suppression and how is it implemented? Point feature detection, descriptor, and matching 1. What is template matching and how is it implemented? (Mathematical expression). What are the limitations of template matching? Can I use it to recognize any car? 2. Similarity metrics: SSD, SAD, NCC, Census transform. What is the intuitive explanation behind SSD and NCC (hint: represent images as vectors)? 3. Feature extraction: what are good feature to track: definition of corners and blobs and their pros and cons. 4. Harris corner detector: intuitive illustration using Moravec definition of corner, flat region, and edge; show how to get to the second moment matrix from the definition of SSD and first order approximation (show that this is a quadratic expression and what is the intuitive interpretation of the second moment matrix using ellipse (what does the ellipse represent?). What is the M matrix for an edge, for a flat region, for an axis-aligned 90-degree corner, and for a non-axisaligned 90-degree corner? What do the eigenvalues of M reveal? Harris detection vs Shi- Tomasi detection. Is Harris rotation, illumination and scale invariant? Why? What is the repeatability of the Harris detector after a recalling of 2? 5. Scale-invariant detection: how does automatic scale selection work? What are the good and the bad properties that a function for automatic scale selection should have or not have? How
3 can we implement scale invariant detection efficiently? (show that we can do this by resampling the image vs rescaling the kernel). What is the Harris Laplacian and what is its repeatability after a rescaling of 2? 6. What is a feature descriptor? (patch of intensity value vs histogram of oriented gradients). How do we match descriptors? 7. SIFT detection and descriptor: how is the keypoint detection done in SIFT and how does this differ from Harris Laplacian? How does SIFT achieve orientation invariance? What is SIFT descriptor built? What is the repeatability of the SIFT detector after a rescaling of 2? And for a 50 degree viewpoint change? Illustrate the 1 st to 2 nd closest ratio of SIFT detection: what s the intuitive reasoning behind it? Where does the 0.8 threshold come from? 8. Brief overview of FAST, SURF, BRIEF, ORB and BRISK. Pros and cons of Harris, SIFT, SURF and FAST and BRIEF, ORB and BRISK in terms of localization accuracy, relocalization, and efficiency (see recap table in the slides). 9. Describe two different ways of tracking features between frames (hint: exercises and VO project). 07 Multiple View Geometry 1. SFM vs 3D reconstruction: definition. 2. Stereo vision: definition of disparity. Simplified case and general case; mathematical expression of depth as a function of baseline, disparity and focal length? Apply error propagation to derive expression of depth uncertainty. How can we improve the uncertainty? Large baseline vs small baseline. What s the closest depth a stereo camera can measure? Can you derive it mathematically? Stereo vision general case: show mathematically how we can compute the intersection of two lines, both linearly and non linearly. What is the geometric interpretation of the linear and non linear approaches and what error term do they minimize? (write it mathematically). Correspondence problem: epipolar geometry; definition of epipole, epipolar line, and epipolar plane. Draw epipolar lines for two converging cameras, for a forward moving camera, for a side-moving camera. 3. Stereo rectification and mathematical derivation of rectifying homographies. 4. Disparity map. How is it computed? 5. How to establish stereo correspondences with subpixel accuracy? 6. Describe one or more simple ways to reject outliers in stereo correspondences. 7. Is stereovision the only way of estimating depth information? If not, list alternative options Multiple view geometry 2 and 3 1. What s the minimum number of correspondences required for calibrated SFM and why? Derive the epipolar constraint. Definition of Essential matrix. The 8-point algorithm (derivation). How many rotation and translation combinations can the essential be decomposed in? Geometric interpretation of the epipolar constraint. Relation between Essential and Fundamental matrix. Normalized 8-point algorithm. Quality metrics for Fundamental matrix estimation (directional error, epipolar line, and reprojection error). 2. RANSAC. Why do we need RANSAC? What is the theoretical maximum number of combinations to explore? After how many iterations can RANSAC be stopped to guarantee a given success probability? What is the trend of RANSAC iterations vs the fraction of outliers and vs the minimum number of points to estimate the model? How do we apply RANSAC to
4 the 8-point algorithm? And to the DLT? How can we reduce the number of RANSAC iterations for the SFM problem (1- and 2-point RANSAC). 3. Definition of Bundle Adjustment (mathematical expression and illustration). Hierarchical SFM. Sequential SFM for monocular VO. What are keyframes? Why do we need them and how can we select them? General definition of VO and comparison with respect VSLAM and SFM. Definition of loop closure detection (why do we need loops?). List the most popular open source VO and VSLAM algorithms. Differences between feature-based and direct methods. 4. RANSAC: In practice, can you fully rely on the formula that predicts the optimal number of iterations? (hint: especially when the inliers themselves are noisy, RANSAC exercise). 5. Why is it important to normalize the point coordinates in the 8-point algorithm? Describe one or more possible ways to achieve this normalization. 10 Multi-view Stereo 1. Working principle (aggregated photometric error). What are the differences in the behavior of the aggregated photometric error for corners, flat regions, and edges? What is the Disparity Space Image (DSI) and how is it built in practice? How do we extract the depth from the DSI? How do we enforce smoothness (regularization) and how do we incorporate depth discontinuities (mathematical expressions)? What happens if we increase lambda (the regularization term)? What if lambda is 0? And if lambda is too big? What is the optimal baseline for multi-view stereo? What are the advantages of GPUs? 11 Tracking 1. Illustrate tracking with block matching. 2. Tracking with differential methods: describe the underlying assumptions, derive the mathematical expression, and meaning of the M matrix. When Is this matrix invertible and when not? What is the aperture problem and how can we overcome it? What is optical flow? 3. Recap of pros and cons of block-based vs differential methods for tracking. Lucas-Kanade algorithm: working principle and derivation of the underlying mathematical expression (only first two slides titled derivation of the Lucas-Kanade algorithm, slide pp ). What is the Hessian matrix and for which warping function does it coincide to that used for point tracking? Discussion on Lucas-Kanade: failure cases and how to overcome them. How do we get the initial guess? Illustration of coarse-to-fine Lucas-Kanade implementation. Illustrate alternative tracking using point features. 4. List one or more possible ways of discarding wrong feature tracks in practice. 12 Place Recognition 1. Bag of words: inverted file index; what is a visual word? Why do we need hierarchical clustering? How does K-means clustering work? Explain and illustrate image retrieval with Bag of Words. Discussion on place recognition: what are the open challenges and what solutions have been proposed? 13 Visual inertial fusion 1. Why an IMU for VO? How does a MEMS IMU work? What s the drift of an industrial IMU? 2. What is the IMU measurement model (formula)? What causes the bias in an IMU? How do we model the bias? How do we integrate the acceleration to get the position (formula)? Loosely
5 coupled vs tightly coupled visual inertial fusion: definition. How can we use non-linear optimization-based approaches to solve for visual inertial fusion (mathematical expression and graphical illustration of the pose graph)? 14 Event-based Vision 1. What s a DVS and how does it work? What are its pros and cons vs standard cameras and vs high speed cameras? Can we apply standard camera calibration techniques? How can we compute optical flow with a DVS? Intuitive explanation of why we can reconstruct the intensity. What is the generative model of a DVS? What is a DAVIS sensor? Can you write the equation of the event generation model and its proof? 15 Visual (inertial) Odometry 1. List one or more possible ways to decide when to triangulate new landmarks based on feature tracks. 2. What are keyframes in Visual Odometry? Why are they needed? Are they strictly necessary? How to decide whether a given frame should be a keyframe? 3. Do you know any popular Visual (Inertial) Odometry algorithm? (one or more). Can you explain briefly how they work? 4. Suppose you have implemented a monocular Visual Odometry pipeline. How would change it to work as well with a stereo camera?
Final Exam Study Guide
Final Exam Study Guide Exam Window: 28th April, 12:00am EST to 30th April, 11:59pm EST Description As indicated in class the goal of the exam is to encourage you to review the material from the course.
More informationDense 3D Reconstruction. Christiano Gava
Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Wide baseline matching (SIFT) Today: dense 3D reconstruction
More informationDense 3D Reconstruction. Christiano Gava
Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Today: dense 3D reconstruction The matching problem
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational
More informationStep-by-Step Model Buidling
Step-by-Step Model Buidling Review Feature selection Feature selection Feature correspondence Camera Calibration Euclidean Reconstruction Landing Augmented Reality Vision Based Control Sparse Structure
More informationLecture 10 Multi-view Stereo (3D Dense Reconstruction) Davide Scaramuzza
Lecture 10 Multi-view Stereo (3D Dense Reconstruction) Davide Scaramuzza REMODE: Probabilistic, Monocular Dense Reconstruction in Real Time, ICRA 14, by Pizzoli, Forster, Scaramuzza [M. Pizzoli, C. Forster,
More informationImage processing and features
Image processing and features Gabriele Bleser gabriele.bleser@dfki.de Thanks to Harald Wuest, Folker Wientapper and Marc Pollefeys Introduction Previous lectures: geometry Pose estimation Epipolar geometry
More informationDirect Methods in Visual Odometry
Direct Methods in Visual Odometry July 24, 2017 Direct Methods in Visual Odometry July 24, 2017 1 / 47 Motivation for using Visual Odometry Wheel odometry is affected by wheel slip More accurate compared
More informationAugmented Reality VU. Computer Vision 3D Registration (2) Prof. Vincent Lepetit
Augmented Reality VU Computer Vision 3D Registration (2) Prof. Vincent Lepetit Feature Point-Based 3D Tracking Feature Points for 3D Tracking Much less ambiguous than edges; Point-to-point reprojection
More informationCamera Drones Lecture 3 3D data generation
Camera Drones Lecture 3 3D data generation Ass.Prof. Friedrich Fraundorfer WS 2017 Outline SfM introduction SfM concept Feature matching Camera pose estimation Bundle adjustment Dense matching Data products
More informationMosaics. Today s Readings
Mosaics VR Seattle: http://www.vrseattle.com/ Full screen panoramas (cubic): http://www.panoramas.dk/ Mars: http://www.panoramas.dk/fullscreen3/f2_mars97.html Today s Readings Szeliski and Shum paper (sections
More informationLecture 10 Dense 3D Reconstruction
Institute of Informatics Institute of Neuroinformatics Lecture 10 Dense 3D Reconstruction Davide Scaramuzza 1 REMODE: Probabilistic, Monocular Dense Reconstruction in Real Time M. Pizzoli, C. Forster,
More informationComputer Vision. Exercise 3 Panorama Stitching 09/12/2013. Compute Vision : Exercise 3 Panorama Stitching
Computer Vision Exercise 3 Panorama Stitching 09/12/2013 Compute Vision : Exercise 3 Panorama Stitching The task Compute Vision : Exercise 3 Panorama Stitching 09/12/2013 2 Pipeline Compute Vision : Exercise
More informationarxiv: v1 [cs.cv] 28 Sep 2018
Camera Pose Estimation from Sequence of Calibrated Images arxiv:1809.11066v1 [cs.cv] 28 Sep 2018 Jacek Komorowski 1 and Przemyslaw Rokita 2 1 Maria Curie-Sklodowska University, Institute of Computer Science,
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 09 130219 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Feature Descriptors Feature Matching Feature
More informationAutonomous Navigation for Flying Robots
Computer Vision Group Prof. Daniel Cremers Autonomous Navigation for Flying Robots Lecture 7.1: 2D Motion Estimation in Images Jürgen Sturm Technische Universität München 3D to 2D Perspective Projections
More informationCS201: Computer Vision Introduction to Tracking
CS201: Computer Vision Introduction to Tracking John Magee 18 November 2014 Slides courtesy of: Diane H. Theriault Question of the Day How can we represent and use motion in images? 1 What is Motion? Change
More informationVisual Odometry. Features, Tracking, Essential Matrix, and RANSAC. Stephan Weiss Computer Vision Group NASA-JPL / CalTech
Visual Odometry Features, Tracking, Essential Matrix, and RANSAC Stephan Weiss Computer Vision Group NASA-JPL / CalTech Stephan.Weiss@ieee.org (c) 2013. Government sponsorship acknowledged. Outline The
More informationStereo and Epipolar geometry
Previously Image Primitives (feature points, lines, contours) Today: Stereo and Epipolar geometry How to match primitives between two (multiple) views) Goals: 3D reconstruction, recognition Jana Kosecka
More informationVisual Tracking (1) Tracking of Feature Points and Planar Rigid Objects
Intelligent Control Systems Visual Tracking (1) Tracking of Feature Points and Planar Rigid Objects Shingo Kagami Graduate School of Information Sciences, Tohoku University swk(at)ic.is.tohoku.ac.jp http://www.ic.is.tohoku.ac.jp/ja/swk/
More informationME/CS 132: Introduction to Vision-based Robot Navigation! Low-level Image Processing" Larry Matthies"
ME/CS 132: Introduction to Vision-based Robot Navigation! Low-level Image Processing" Larry Matthies" lhm@jpl.nasa.gov, 818-354-3722" Announcements" First homework grading is done! Second homework is due
More informationStructure from Motion. Introduction to Computer Vision CSE 152 Lecture 10
Structure from Motion CSE 152 Lecture 10 Announcements Homework 3 is due May 9, 11:59 PM Reading: Chapter 8: Structure from Motion Optional: Multiple View Geometry in Computer Vision, 2nd edition, Hartley
More informationEXAM SOLUTIONS. Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006,
School of Computer Science and Communication, KTH Danica Kragic EXAM SOLUTIONS Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006, 14.00 19.00 Grade table 0-25 U 26-35 3 36-45
More information55:148 Digital Image Processing Chapter 11 3D Vision, Geometry
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry Topics: Basics of projective geometry Points and hyperplanes in projective space Homography Estimating homography from point correspondence
More informationStereo Vision. MAN-522 Computer Vision
Stereo Vision MAN-522 Computer Vision What is the goal of stereo vision? The recovery of the 3D structure of a scene using two or more images of the 3D scene, each acquired from a different viewpoint in
More informationFinal Exam Study Guide CSE/EE 486 Fall 2007
Final Exam Study Guide CSE/EE 486 Fall 2007 Lecture 2 Intensity Sufaces and Gradients Image visualized as surface. Terrain concepts. Gradient of functions in 1D and 2D Numerical derivatives. Taylor series.
More informationOutline 7/2/201011/6/
Outline Pattern recognition in computer vision Background on the development of SIFT SIFT algorithm and some of its variations Computational considerations (SURF) Potential improvement Summary 01 2 Pattern
More informationIndex. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 263
Index 3D reconstruction, 125 5+1-point algorithm, 284 5-point algorithm, 270 7-point algorithm, 265 8-point algorithm, 263 affine point, 45 affine transformation, 57 affine transformation group, 57 affine
More information1 Projective Geometry
CIS8, Machine Perception Review Problem - SPRING 26 Instructions. All coordinate systems are right handed. Projective Geometry Figure : Facade rectification. I took an image of a rectangular object, and
More informationComputational Optical Imaging - Optique Numerique. -- Single and Multiple View Geometry, Stereo matching --
Computational Optical Imaging - Optique Numerique -- Single and Multiple View Geometry, Stereo matching -- Autumn 2015 Ivo Ihrke with slides by Thorsten Thormaehlen Reminder: Feature Detection and Matching
More informationCapturing, Modeling, Rendering 3D Structures
Computer Vision Approach Capturing, Modeling, Rendering 3D Structures Calculate pixel correspondences and extract geometry Not robust Difficult to acquire illumination effects, e.g. specular highlights
More informationAugmented Reality, Advanced SLAM, Applications
Augmented Reality, Advanced SLAM, Applications Prof. Didier Stricker & Dr. Alain Pagani alain.pagani@dfki.de Lecture 3D Computer Vision AR, SLAM, Applications 1 Introduction Previous lectures: Basics (camera,
More informationLocal features and image matching. Prof. Xin Yang HUST
Local features and image matching Prof. Xin Yang HUST Last time RANSAC for robust geometric transformation estimation Translation, Affine, Homography Image warping Given a 2D transformation T and a source
More informationMaster Automática y Robótica. Técnicas Avanzadas de Vision: Visual Odometry. by Pascual Campoy Computer Vision Group
Master Automática y Robótica Técnicas Avanzadas de Vision: by Pascual Campoy Computer Vision Group www.vision4uav.eu Centro de Automá
More informationFinal Review CMSC 733 Fall 2014
Final Review CMSC 733 Fall 2014 We have covered a lot of material in this course. One way to organize this material is around a set of key equations and algorithms. You should be familiar with all of these,
More informationLocal features: detection and description May 12 th, 2015
Local features: detection and description May 12 th, 2015 Yong Jae Lee UC Davis Announcements PS1 grades up on SmartSite PS1 stats: Mean: 83.26 Standard Dev: 28.51 PS2 deadline extended to Saturday, 11:59
More informationMidterm Examination CS 534: Computational Photography
Midterm Examination CS 534: Computational Photography November 3, 2016 NAME: Problem Score Max Score 1 6 2 8 3 9 4 12 5 4 6 13 7 7 8 6 9 9 10 6 11 14 12 6 Total 100 1 of 8 1. [6] (a) [3] What camera setting(s)
More informationIndex. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 253
Index 3D reconstruction, 123 5+1-point algorithm, 274 5-point algorithm, 260 7-point algorithm, 255 8-point algorithm, 253 affine point, 43 affine transformation, 55 affine transformation group, 55 affine
More informationComputational Optical Imaging - Optique Numerique. -- Multiple View Geometry and Stereo --
Computational Optical Imaging - Optique Numerique -- Multiple View Geometry and Stereo -- Winter 2013 Ivo Ihrke with slides by Thorsten Thormaehlen Feature Detection and Matching Wide-Baseline-Matching
More informationAll good things must...
Lecture 17 Final Review All good things must... UW CSE vision faculty Course Grading Programming Projects (80%) Image scissors (20%) -DONE! Panoramas (20%) - DONE! Content-based image retrieval (20%) -
More informationLive Metric 3D Reconstruction on Mobile Phones ICCV 2013
Live Metric 3D Reconstruction on Mobile Phones ICCV 2013 Main Contents 1. Target & Related Work 2. Main Features of This System 3. System Overview & Workflow 4. Detail of This System 5. Experiments 6.
More informationThe SIFT (Scale Invariant Feature
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor developed by David Lowe University of British Columbia Initial paper ICCV 1999 Newer journal paper IJCV 2004 Review: Matt Brown s Canonical
More informationSIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014
SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT SIFT: Scale Invariant Feature Transform; transform image
More informationLocal features: detection and description. Local invariant features
Local features: detection and description Local invariant features Detection of interest points Harris corner detection Scale invariant blob detection: LoG Description of local patches SIFT : Histograms
More informationEdge and corner detection
Edge and corner detection Prof. Stricker Doz. G. Bleser Computer Vision: Object and People Tracking Goals Where is the information in an image? How is an object characterized? How can I find measurements
More informationCS5670: Computer Vision
CS5670: Computer Vision Noah Snavely Lecture 4: Harris corner detection Szeliski: 4.1 Reading Announcements Project 1 (Hybrid Images) code due next Wednesday, Feb 14, by 11:59pm Artifacts due Friday, Feb
More informationFeatures Points. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE)
Features Points Andrea Torsello DAIS Università Ca Foscari via Torino 155, 30172 Mestre (VE) Finding Corners Edge detectors perform poorly at corners. Corners provide repeatable points for matching, so
More informationComputer Vision for HCI. Topics of This Lecture
Computer Vision for HCI Interest Points Topics of This Lecture Local Invariant Features Motivation Requirements, Invariances Keypoint Localization Features from Accelerated Segment Test (FAST) Harris Shi-Tomasi
More information3D Photography. Marc Pollefeys, Torsten Sattler. Spring 2015
3D Photography Marc Pollefeys, Torsten Sattler Spring 2015 Schedule (tentative) Feb 16 Feb 23 Mar 2 Mar 9 Mar 16 Mar 23 Mar 30 Apr 6 Apr 13 Apr 20 Apr 27 May 4 May 11 May 18 May 25 Introduction Geometry,
More informationImage correspondences and structure from motion
Image correspondences and structure from motion http://graphics.cs.cmu.edu/courses/15-463 15-463, 15-663, 15-862 Computational Photography Fall 2017, Lecture 20 Course announcements Homework 5 posted.
More informationTowards a visual perception system for LNG pipe inspection
Towards a visual perception system for LNG pipe inspection LPV Project Team: Brett Browning (PI), Peter Rander (co PI), Peter Hansen Hatem Alismail, Mohamed Mustafa, Joey Gannon Qri8 Lab A Brief Overview
More informationBSB663 Image Processing Pinar Duygulu. Slides are adapted from Selim Aksoy
BSB663 Image Processing Pinar Duygulu Slides are adapted from Selim Aksoy Image matching Image matching is a fundamental aspect of many problems in computer vision. Object or scene recognition Solving
More informationMultiple View Geometry
Multiple View Geometry CS 6320, Spring 2013 Guest Lecture Marcel Prastawa adapted from Pollefeys, Shah, and Zisserman Single view computer vision Projective actions of cameras Camera callibration Photometric
More informationDealing with Scale. Stephan Weiss Computer Vision Group NASA-JPL / CalTech
Dealing with Scale Stephan Weiss Computer Vision Group NASA-JPL / CalTech Stephan.Weiss@ieee.org (c) 2013. Government sponsorship acknowledged. Outline Why care about size? The IMU as scale provider: The
More informationObject Recognition with Invariant Features
Object Recognition with Invariant Features Definition: Identify objects or scenes and determine their pose and model parameters Applications Industrial automation and inspection Mobile robots, toys, user
More informationBuilding a Panorama. Matching features. Matching with Features. How do we build a panorama? Computational Photography, 6.882
Matching features Building a Panorama Computational Photography, 6.88 Prof. Bill Freeman April 11, 006 Image and shape descriptors: Harris corner detectors and SIFT features. Suggested readings: Mikolajczyk
More informationcalibrated coordinates Linear transformation pixel coordinates
1 calibrated coordinates Linear transformation pixel coordinates 2 Calibration with a rig Uncalibrated epipolar geometry Ambiguities in image formation Stratified reconstruction Autocalibration with partial
More informationOverview. Augmented reality and applications Marker-based augmented reality. Camera model. Binary markers Textured planar markers
Augmented reality Overview Augmented reality and applications Marker-based augmented reality Binary markers Textured planar markers Camera model Homography Direct Linear Transformation What is augmented
More informationHomographies and RANSAC
Homographies and RANSAC Computer vision 6.869 Bill Freeman and Antonio Torralba March 30, 2011 Homographies and RANSAC Homographies RANSAC Building panoramas Phototourism 2 Depth-based ambiguity of position
More informationLocal invariant features
Local invariant features Tuesday, Oct 28 Kristen Grauman UT-Austin Today Some more Pset 2 results Pset 2 returned, pick up solutions Pset 3 is posted, due 11/11 Local invariant features Detection of interest
More informationLocal Feature Detectors
Local Feature Detectors Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr Slides adapted from Cordelia Schmid and David Lowe, CVPR 2003 Tutorial, Matthew Brown,
More informationVisual Navigation for Flying Robots. Structure From Motion
Computer Vision Group Prof. Daniel Cremers Visual Navigation for Flying Robots Structure From Motion Dr. Jürgen Sturm VISNAV Oral Team Exam Date and Time Student Name Student Name Student Name Mon, July
More informationVisual Tracking (1) Pixel-intensity-based methods
Intelligent Control Systems Visual Tracking (1) Pixel-intensity-based methods Shingo Kagami Graduate School of Information Sciences, Tohoku University swk(at)ic.is.tohoku.ac.jp http://www.ic.is.tohoku.ac.jp/ja/swk/
More informationMonocular Visual-Inertial SLAM. Shaojie Shen Assistant Professor, HKUST Director, HKUST-DJI Joint Innovation Laboratory
Monocular Visual-Inertial SLAM Shaojie Shen Assistant Professor, HKUST Director, HKUST-DJI Joint Innovation Laboratory Why Monocular? Minimum structural requirements Widely available sensors Applications:
More informationA System of Image Matching and 3D Reconstruction
A System of Image Matching and 3D Reconstruction CS231A Project Report 1. Introduction Xianfeng Rui Given thousands of unordered images of photos with a variety of scenes in your gallery, you will find
More informationCamera Geometry II. COS 429 Princeton University
Camera Geometry II COS 429 Princeton University Outline Projective geometry Vanishing points Application: camera calibration Application: single-view metrology Epipolar geometry Application: stereo correspondence
More informationNonlinear State Estimation for Robotics and Computer Vision Applications: An Overview
Nonlinear State Estimation for Robotics and Computer Vision Applications: An Overview Arun Das 05/09/2017 Arun Das Waterloo Autonomous Vehicles Lab Introduction What s in a name? Arun Das Waterloo Autonomous
More informationVisual Tracking (1) Feature Point Tracking and Block Matching
Intelligent Control Systems Visual Tracking (1) Feature Point Tracking and Block Matching Shingo Kagami Graduate School of Information Sciences, Tohoku University swk(at)ic.is.tohoku.ac.jp http://www.ic.is.tohoku.ac.jp/ja/swk/
More informationLecture 14: Basic Multi-View Geometry
Lecture 14: Basic Multi-View Geometry Stereo If I needed to find out how far point is away from me, I could use triangulation and two views scene point image plane optical center (Graphic from Khurram
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 12 130228 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Panoramas, Mosaics, Stitching Two View Geometry
More informationComputer Vision I - Appearance-based Matching and Projective Geometry
Computer Vision I - Appearance-based Matching and Projective Geometry Carsten Rother 01/11/2016 Computer Vision I: Image Formation Process Roadmap for next four lectures Computer Vision I: Image Formation
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 10 130221 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Canny Edge Detector Hough Transform Feature-Based
More informationAutomatic Image Alignment (feature-based)
Automatic Image Alignment (feature-based) Mike Nese with a lot of slides stolen from Steve Seitz and Rick Szeliski 15-463: Computational Photography Alexei Efros, CMU, Fall 2006 Today s lecture Feature
More informationA Systems View of Large- Scale 3D Reconstruction
Lecture 23: A Systems View of Large- Scale 3D Reconstruction Visual Computing Systems Goals and motivation Construct a detailed 3D model of the world from unstructured photographs (e.g., Flickr, Facebook)
More informationDigital Image Processing COSC 6380/4393
Digital Image Processing COSC 6380/4393 Lecture 21 Nov 16 th, 2017 Pranav Mantini Ack: Shah. M Image Processing Geometric Transformation Point Operations Filtering (spatial, Frequency) Input Restoration/
More informationComputer Vision Lecture 20
Computer Perceptual Vision and Sensory WS 16/17 Augmented Computing Computer Perceptual Vision and Sensory WS 16/17 Augmented Computing Computer Perceptual Vision and Sensory WS 16/17 Augmented Computing
More informationCS 231A Computer Vision (Winter 2018) Problem Set 3
CS 231A Computer Vision (Winter 2018) Problem Set 3 Due: Feb 28, 2018 (11:59pm) 1 Space Carving (25 points) Dense 3D reconstruction is a difficult problem, as tackling it from the Structure from Motion
More informationCS231A Midterm Review. Friday 5/6/2016
CS231A Midterm Review Friday 5/6/2016 Outline General Logistics Camera Models Non-perspective cameras Calibration Single View Metrology Epipolar Geometry Structure from Motion Active Stereo and Volumetric
More informationMatching. Compare region of image to region of image. Today, simplest kind of matching. Intensities similar.
Matching Compare region of image to region of image. We talked about this for stereo. Important for motion. Epipolar constraint unknown. But motion small. Recognition Find object in image. Recognize object.
More informationFeature Tracking and Optical Flow
Feature Tracking and Optical Flow Prof. D. Stricker Doz. G. Bleser Many slides adapted from James Hays, Derek Hoeim, Lana Lazebnik, Silvio Saverse, who 1 in turn adapted slides from Steve Seitz, Rick Szeliski,
More informationChapter 3 Image Registration. Chapter 3 Image Registration
Chapter 3 Image Registration Distributed Algorithms for Introduction (1) Definition: Image Registration Input: 2 images of the same scene but taken from different perspectives Goal: Identify transformation
More informationDavide Scaramuzza. University of Zurich
Davide Scaramuzza University of Zurich Robotics and Perception Group http://rpg.ifi.uzh.ch/ Scaramuzza, D., Fraundorfer, F., Visual Odometry: Part I - The First 30 Years and Fundamentals, IEEE Robotics
More informationStructure from motion
Structure from motion Structure from motion Given a set of corresponding points in two or more images, compute the camera parameters and the 3D point coordinates?? R 1,t 1 R 2,t R 2 3,t 3 Camera 1 Camera
More informationCS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry
CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry Some material taken from: David Lowe, UBC Jiri Matas, CMP Prague http://cmp.felk.cvut.cz/~matas/papers/presentations/matas_beyondransac_cvprac05.ppt
More informationMulti-stable Perception. Necker Cube
Multi-stable Perception Necker Cube Spinning dancer illusion, Nobuyuki Kayahara Multiple view geometry Stereo vision Epipolar geometry Lowe Hartley and Zisserman Depth map extraction Essential matrix
More informationLecture 16: Computer Vision
CS4442/9542b: Artificial Intelligence II Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field
More information3D Vision. Viktor Larsson. Spring 2019
3D Vision Viktor Larsson Spring 2019 Schedule Feb 18 Feb 25 Mar 4 Mar 11 Mar 18 Mar 25 Apr 1 Apr 8 Apr 15 Apr 22 Apr 29 May 6 May 13 May 20 May 27 Introduction Geometry, Camera Model, Calibration Features,
More informationMidterm Wed. Local features: detection and description. Today. Last time. Local features: main components. Goal: interest operator repeatability
Midterm Wed. Local features: detection and description Monday March 7 Prof. UT Austin Covers material up until 3/1 Solutions to practice eam handed out today Bring a 8.5 11 sheet of notes if you want Review
More informationFeature Based Registration - Image Alignment
Feature Based Registration - Image Alignment Image Registration Image registration is the process of estimating an optimal transformation between two or more images. Many slides from Alexei Efros http://graphics.cs.cmu.edu/courses/15-463/2007_fall/463.html
More informationCS 532: 3D Computer Vision 7 th Set of Notes
1 CS 532: 3D Computer Vision 7 th Set of Notes Instructor: Philippos Mordohai Webpage: www.cs.stevens.edu/~mordohai E-mail: Philippos.Mordohai@stevens.edu Office: Lieb 215 Logistics No class on October
More informationComputer Vision Lecture 20
Computer Perceptual Vision and Sensory WS 16/76 Augmented Computing Many slides adapted from K. Grauman, S. Seitz, R. Szeliski, M. Pollefeys, S. Lazebnik Computer Vision Lecture 20 Motion and Optical Flow
More informationVisual Pose Estimation System for Autonomous Rendezvous of Spacecraft
Visual Pose Estimation System for Autonomous Rendezvous of Spacecraft Mark A. Post1, Junquan Li2, and Craig Clark2 Space Mechatronic Systems Technology Laboratory Dept. of Design, Manufacture & Engineering
More informationCSE 252B: Computer Vision II
CSE 252B: Computer Vision II Lecturer: Serge Belongie Scribes: Jeremy Pollock and Neil Alldrin LECTURE 14 Robust Feature Matching 14.1. Introduction Last lecture we learned how to find interest points
More informationGeometric Reconstruction Dense reconstruction of scene geometry
Lecture 5. Dense Reconstruction and Tracking with Real-Time Applications Part 2: Geometric Reconstruction Dr Richard Newcombe and Dr Steven Lovegrove Slide content developed from: [Newcombe, Dense Visual
More informationORB SLAM 2 : an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
ORB SLAM 2 : an OpenSource SLAM System for Monocular, Stereo and RGBD Cameras Raul urartal and Juan D. Tardos Presented by: Xiaoyu Zhou Bolun Zhang Akshaya Purohit Lenord Melvix 1 Outline Background Introduction
More informationProf. Feng Liu. Spring /26/2017
Prof. Feng Liu Spring 2017 http://www.cs.pdx.edu/~fliu/courses/cs510/ 04/26/2017 Last Time Re-lighting HDR 2 Today Panorama Overview Feature detection Mid-term project presentation Not real mid-term 6
More informationComputer Vision I. Announcement. Stereo Vision Outline. Stereo II. CSE252A Lecture 15
Announcement Stereo II CSE252A Lecture 15 HW3 assigned No class on Thursday 12/6 Extra class on Tuesday 12/4 at 6:30PM in WLH Room 2112 Mars Exploratory Rovers: Spirit and Opportunity Stereo Vision Outline
More informationComputer Vision Lecture 20
Computer Vision Lecture 2 Motion and Optical Flow Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de 28.1.216 Man slides adapted from K. Grauman, S. Seitz, R. Szeliski,
More informationIntroduction. Introduction. Related Research. SIFT method. SIFT method. Distinctive Image Features from Scale-Invariant. Scale.
Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe presented by, Sudheendra Invariance Intensity Scale Rotation Affine View point Introduction Introduction SIFT (Scale Invariant Feature
More informationLocal Features: Detection, Description & Matching
Local Features: Detection, Description & Matching Lecture 08 Computer Vision Material Citations Dr George Stockman Professor Emeritus, Michigan State University Dr David Lowe Professor, University of British
More information